© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125040
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arkin
    -0.07
    .MESSAGE
    -0.07
    .camel
    -0.06
    ÛĮدÛĮ
    -0.06
     ourselves
    -0.06
    WARN
    -0.06
    íĨµ
    -0.06
    esian
    -0.06
    جا
    -0.06
    ewise
    -0.06
    POSITIVE LOGITS
     injuries
    0.08
    ologne
    0.07
    SCP
    0.07
    __/
    0.06
     sustained
    0.06
     shock
    0.06
    lesc
    0.06
    æłª
    0.06
    ">//
    0.06
    é½
    0.06
    Activations Density 0.009%

    No Known Activations